I am a Machine Learning Researcher specializing in Generative AI and 3D Computer Vision, currently working at Huawei's 3D Vision Team. My primary research focus is video diffusion models — including DiT-based video architectures, flow matching at the training level, and diffusion distillation — alongside 3D/4D Gaussian Splatting and feed-forward reconstruction pipelines (DUSt3R, MASt3R, InstantSplat). I have additional work on video diffusion currently under review at top CV venues.

Previously, I contributed to Ubisoft La Forge as an R&D Intern, where I developed a geometry-aware texture synthesis tool for digital avatar creation using differentiable shading — work that led to publications at CVPR 2024 and CVPR Workshop 2025.

I hold a Master's degree in Electrical and Computer Engineering from York University, where I was advised by Prof. Nikolaus Troje and co-advised by Prof. Marcus A. Brubaker. My thesis focused on AI-assisted pipelines for 3D face avatar generation.

As a Vector Faculty Affiliate Researcher, I work at the intersection of generative modeling, neural rendering, and computer vision. My broader expertise includes autoregressive video generation, VLM-conditioned synthesis, face and avatar generation, and distributed training at scale (FSDP, DeepSpeed).